• Journal of Information Processing Systems
• /
• v.15 no.5
• /
• pp.1218-1230
• /
• 2019

This study proposes a novel video traffic flow detection method based on machine vision technology. The three-frame difference method, which is one kind of a motion evaluation method, is used to establish initial background image, and then a statistical scoring strategy is chosen to update background image in real time. Finally, the background difference method is used for detecting the moving objects. Meanwhile, a simple but effective shadow elimination method is introduced to improve the accuracy of the detection for moving objects. Furthermore, the study also proposes a vehicle matching and tracking strategy by combining characteristics, such as vehicle's location information, color information and fractal dimension information. Experimental results show that this detection method could quickly and effectively detect various traffic flow parameters, laying a solid foundation for enhancing the degree of automation for traffic management.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.6
• /
• pp.2444-2463
• /
• 2020

Significant detection of video can more rationally allocate computing resources and reduce the amount of computation to improve accuracy. Deep learning can extract the edge features of the image, providing technical support for video saliency. This paper proposes a new detection method. We combine the Convolutional Neural Network (CNN) and the Deep Bidirectional LSTM Network (DB-LSTM) to learn the spatio-temporal features by exploring the object motion information and object motion information to generate video. A continuous frame of significant images. We also analyzed the sample database and found that human attention and significant conversion are time-dependent, so we also considered the significance detection of video cross-frame. Finally, experiments show that our method is superior to other advanced methods.

• Journal of Information Processing Systems
• /
• v.19 no.1
• /
• pp.80-88
• /
• 2023

RGB-thermal (RGB-T) tracking using unmanned aerial vehicles (UAVs) involves challenges with regards to the similarity of objects, occlusion, fast motion, and motion blur, among other issues. In this study, we propose dynamic tracking aggregation (DTA) as a unified framework to perform object detection and data association. The proposed approach obtains fused features based a transformer model and an L1-norm strategy. To link the current frame with recent information, a dynamically updated embedding called dynamic tracking identification (DTID) is used to model the iterative tracking process. For object association, we designed a long short-term tracking aggregation module for dynamic feature propagation to match spatial and temporal embeddings. DTA achieved a highly competitive performance in an experimental evaluation on public benchmark datasets.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.845-848
• /
• 2003

There are many researches on using human neuro-biological signals for various problems such as controlling a mechanical object and/or interfacing human with the computer. It is one of very interesting topics that human can use various instruments without learning specific knowledge if the instruments can be controlled as human intends. In this paper, we proposed an intelligent motion planner for a redundant manipulator, which is controlled by humans neuro-biological signals, especially, EOG (Electrooculogram). We found the optimal motion planner for the redundant manipulator that can move to the desired point. We used neural networks to find the inverse kinematics solution of the manipulator. We also showed the performance of the proposed motion planner with several simulations.

• Proceedings of the IEEK Conference
• /
• 1998.10a
• /
• pp.955-958
• /
• 1998

This paper describes the algorithm which extracts moving vehicles from sequential images and tracks those vehicles using Kalman filter. This work is composed of a motion segmentation stage which extracts moving objects from sequential images and gets features of objects, and a motion estimation stage which estimates the position and the motion of moving objects using Kalman filter. In the motion estimation stage, applying to affine motion model we divided the Kalman filter into position filter and velocity filter to employ linear Kalman filter. Multi-target tracking requires a data association component that decides which measurement to use for updating the state of which object. We use pattern recognition method to solve this problem.

• The Journal of Korean Physical Therapy
• /
• v.17 no.2
• /
• pp.1-10
• /
• 2005

This study is going to have been recognized a change of Cervical range of motion with the object 40 persons who sat for many hours before computer. According to the therapy term, sling used joint mobility exercise and Mckenzie was executed by 20 persons Shared. The study results about the effect that Cervical exercise had on joint Range of motion of a VDT syndrome patient were as follows. 1. There was a similar difference a sling used in Cervical Range of motion of joint mobility exercise cure after one-week, two-weet and three-week. 2. The change Cervical Range of motion of Mckenzie exercise has not been after one-week and two-week but a similar difference happens after three-week. 3. There has not been difference between joint mobility exercise and Mckenzie exercise in cure ferm sling used.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2001.04a
• /
• pp.9-14
• /
• 2001

A new model utilizing a transfer function is introduced in the present paper for analizing motion errors of hydrostatic tables. Relationship between film reaction force in a single hydrostatic pad and form error of a guide rail is derived at various spacial frequencies by finite element analysis, and it is expressed as a transfer function. This transfer function clarifies so called averaging effect of the oil film quantitively. For example, it is found that the amplitide of the film reaction force is reduced as the spacial frequency increases or relative width of the pocket is reduced. Motion errors of a multiple pad table is estimated from transfer function, geometric relationship between each pads and form errors of a guide rail, which is named as Transfer Function Method. Calculated motion errors by TFM show good agreement with motion errors calculated by Multi Pad Method, which is considered entire table as an analysis object. From the results, it is confirmed that the proposed TFM is very effective to analyze the motion errors of hydrostatic tables.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1998.06a
• /
• pp.3-8
• /
• 1998

The conversion of monoscopic video to 3D stereoscopic video has been studied by some pioneering researchers. In spite of the commercial of potential of the technology, two problems have bothered the progress of this research area: vertical motion parallax and high computational complexity. The former causes the low 3D perception, while the hardware complexity is required by the latter. The previous research has dealt with NTSC video, thur requiring complex processing steps, one of which is motion estimation. This paper proposes 3D stereoscopic conversion method of MPGE encoded data. Our proposed method has the advantage that motion estimation can be avoided by processing MPEG compressed data for the extraction of motion data as well as that camera and object motion in random in random directions can be handled.

• Journal of the Korean Society for Precision Engineering
• /
• v.23 no.7 s.184
• /
• pp.67-75
• /
• 2006

One of challenging topics for humanoid hands is to modulate a human-like motion of humanoid fingers handling an object. To this end, recognizing the motion behavior of human fingers is very important aspect. Based on this concept, this paper identifies the .joint trajectories of human fingers for an operation of hand opening and closing, and specifies an empirical model that coordinates an inter-articular relationship of human fingers doing the given motion. It is expected that the inter-articular model presented in this paper is applicable for humanoid fingers to mimic the natural motion of human fingers.

• Proceedings of the IEEK Conference
• /
• 2002.06d
• /
• pp.17-20
• /
• 2002

The methods that track and detect motion field based on image difference of successive images from camera can separate motion field and background effectively, but because of noise and background images getting proper difference images is hard to achieve. In this paper we propose a method that can improve difference image quality significantly. Three step process is used. At the first step, existence of motion field is determined, the second step is finding proper threshold value using 'Contrast Streching' technique which enables us to find proper motion field even in complex images. At last step, remaining noise is removed and motion field is determined.